SOURCE-LINKED INTELLIGENCE

Improving Cross-Lingual Token Representations by Adding a Pinch of SALT

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Cross-lingual sentence encoders enable scalable transfer across hundreds of languages, powering applications such as translation mining and zero-shot learning in low-resource settings. Although trained for sentence-level alignment, they are increasingly also applied to token-level tasks such as hallucination detection and sequence tagging, exposing a mismatch between training and usage. We propose SALT, a lightweight post-training method that improves token representations by injecting span-level supervision into existing sentence encoders. Across five multilingual token-level benchmarks, SALT

Read original source ↗ Open in workspace

recordType

paper

region

Global